4 papers
Spectrally Deconfounded Gradient Boosting
Andrea Nava, Peter Bühlmann, Fabio Sigrist
Flexible machine-learning methods can be sensitive to hidden confounding: they may learn associations induced by unobserved confounders rather than stable signals. Spectral deconfo…
A Censored Transformed Model for Proportional Outcomes with Boundary Mass and an Application to Loss Given Default Modeling
Yuan Christopher Qiang, Fabio Sigrist
We introduce the zero-one censored transformed normal (ZOC-TN) model for proportional responses with potential probability mass at the boundaries 0 and 1. The model combines a cens…
A new framework for non-stationary spatio-temporal data fusion of multi-fidelity models
Pietro Colombo, Fabio Sigrist, Claire Miller +3
We propose a new scalable framework for spatio-temporal data fusion with multi-fidelity Gaussian processes (MFGPs) that enables fully likelihood-based inference for both stationary…
A Spatio-Temporal Machine Learning Model for Mortgage Credit Risk: Default Probabilities and Loan Portfolios
Pascal Kündig, Fabio Sigrist
We introduce a novel machine learning model for credit risk by combining tree-boosting with a latent spatio-temporal Gaussian process model accounting for frailty correlation. This…